Maya Moore is a hero.

Because this is a good use of time on Saturday night, I want to just pull out this 2016 post-mortem from the pollsters' professional org (full disclosure, I'm a member), which examines in depth the possibility for a shy Trump vote. Short version: tests “yielded no evidence.”

Good piece from a great writer. A suggestion to fellow readers: read the article but skip the replies/comments.

Sebastian Aho is so damn good.

NEW: Here are some key points the public should know about polling heading into this year’s presidential election. pewrsr.ch/2DyEi3N

Touki Toussaint, Two Pitch Curveball Sequence. Quick Pitch 76mph Curveball (ball), Vlad Jr. nods/smiles. Filthy 79mph Curveball, Vlad Jr. sword. ⚔️

Reviews of 2016 polling found that failing to adjust for overrepresentation of college grads was among the reasons many state-level polls underestimated Trump's support. Our new report provides data on the education profile of voters in all 50 states + DC: pewresearch.org/methods/2020/0…

Every other political science sub-specialty: “what we study is much more consequential than you think it is!” Misinformation scholars: “what we study is much less consequential than you think it is!”

We had some thoughts about what might have gone wrong with the polls last week -- and what the causes might mean for polling on policy issues pewrsr.ch/3f0Z7mT

Big day at Pew Research Center with a new post from Pew Research Fact Tank: women make up just over a quarter of all members of the 117th Congress - the highest percentage in U.S. history pewrsr.ch/2Lp3XMa

If you're going to do this to two of your best players (one of which is coming off colon cancer surgery) so you can save $1.5 mil next year, sell the team. The word "embarrassing" doesn't do this justice.

We wondered: What do election poll errors like those in 2020 mean for the accuracy of polls about issues? To find out, we conducted a simulation. Long story short: Big overestimates of Biden’s margin translate into only small errors in issue questions pewrsr.ch/3b5oJ1I

For our survey research pals: After struggling to find reliable, current benchmarks for vital traits like party ID and religious affil., we decided to invest in benchmarking them ourselves. NPORS, the Nat'l Public Opinion Reference Survey Pew Research Center buff.ly/2PMKcVc

NEW: Jewish Americans in 2020 pewrsr.ch/3uCWtL6

tidycensus and the segregation package by @elbersb make a great combination for analysis of residential segregation in #rstats. Multigroup entropy indices and the dissimilarity index are straightforward to compute.

NEW: We conduct lots of opinion polls. We also do research on how to improve polling. We’ve tried to distill all this knowledge into short, easy-to-digest lessons we hope will answer your questions. Read more about our new email mini-course on polling: pewresearch.org/fact-tank/2021…

seeing how hype ronnie get for his team while they play in the world series without him just makes me love him even more than i already did x.com/tuckersupremac…

Do you ever *just know* you've written a line of code somewhere, but you can't find it? Use Ctrl+Shift+F in RStudio to search for terms *within* #rstats scripts (and other files), then send a thank you to the good people at Posit PBC